The result is not that ideal like the paper showed

Open Jarvis-K opened this issue 7 years ago • 3 comments

I just run maddpg in simple_speaker_listener several times,but none of them get the -20 avg-reward like the paper proposed. Are there anything i should modify to get a better or more stable result?

Oct 26 '18 06:10 Jarvis-K

Looks like you're not the only one having trouble reproducing some results: #12

Nov 21 '18 14:11 4rzael

I am getting -60 rewards, is that normal for just running the code without any alternations?

Jun 07 '19 18:06 BolunDai0216

Also, in scenario=simple_speaker_listener, this code cannot converge to the result reported in Fig.4. Anyone knows the problem?

Nov 14 '19 05:11 KK666-AI